Title :
The 9th annual MLSP competition: Second place
Author :
Hong Wei Ng ; Thi Ngoc Tho Nguyen
Author_Institution :
Adv. Digital Sci. Center (ADSC), Univ. of Illinois at Urbana-Champaign, Singapore, Singapore
Abstract :
The MLSP 2013 Bird Classification Challenge requires participants to predict the set of bird species present in audio clips in a given test set, with the aim of maximizing the micro-AUC score computed from the predictions. This report summarizes the 2nd place solution by team Herbal Candy that achieved a micro-AUC score of 0.95050.
Keywords :
audio signal processing; learning (artificial intelligence); signal classification; MLSP 2013 Bird Classification Challenge; area under the characteristic curve; audio clips; bird species; machine learning for signal processing; micro-AUC score; Birds; Computational modeling; Noise; Noise measurement; Spectrogram; Training; Vegetation; Audio classification;
Conference_Titel :
Machine Learning for Signal Processing (MLSP), 2013 IEEE International Workshop on
Conference_Location :
Southampton
DOI :
10.1109/MLSP.2013.6661933
